GuidesAI Agents

Running Agents on Brev

View as Markdown

Deploy AI agents on Brev CPU instances for sandboxed execution environments. CPU instances provide isolated, cost-effective compute for agent workloads that don’t require GPU acceleration.

Prerequisites

Deploy an Agent Sandbox

Option A: Deploy from a Launchable

Use a pre-built Launchable to get started quickly:

  • NemoClaw Agent — the NVIDIA agent framework for tool-use and code execution
  • Generic Agent Sandbox — a blank CPU sandbox for custom agent deployments

Browse available Launchables at brev.nvidia.com. Select a CPU instance type and deploy.

Option B: Provision Manually

Create a CPU instance through the Brev Console or CLI:

$brev create my-agent

Select a CPU instance type (no GPU) when prompted, or specify one in the Brev Console.

Connect and Verify

1

Connect to your instance

After the instance is running, connect with the CLI:

$brev shell my-agent
2

Verify the agent is running

Check that your agent process is active:

$# Check running processes
$ps aux | grep agent
$
$# Check Docker containers if using containerized agents
$docker ps

CPU vs GPU for Agents

Use CaseRecommendedWhy
Code execution / sandboxesCPU instanceNo GPU needed, lower cost.
Web browsing / scrapingCPU instanceNetwork-bound, not compute-bound.
Tool use / API callsCPU instanceMinimal compute requirements.
LLM inference (self-hosted)GPU instanceModels require GPU acceleration.
Vision / image processingGPU instanceGPU accelerates image operations.
Training / fine-tuningGPU instanceRequires GPU compute.

What’s Next?

CPU Instances

Learn about CPU instance lifecycle, supported types, and billing.

Launchables

Create and share one-click deployable agent environments.